What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Yujie, Yu, Zhuoyun, Wang, Xuehai, Zhu, Yuqi, Zhang, Ningyu, Wei, Lanning, Du, Lun, Zheng, Da, Chen, Huajun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915944037613568
author Luo, Yujie
Yu, Zhuoyun
Wang, Xuehai
Zhu, Yuqi
Zhang, Ningyu
Wei, Lanning
Du, Lun
Zheng, Da
Chen, Huajun
author_facet Luo, Yujie
Yu, Zhuoyun
Wang, Xuehai
Zhu, Yuqi
Zhang, Ningyu
Wei, Lanning
Du, Lun
Zheng, Da
Chen, Huajun
contents Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of retrieval-augmented generation (RAG) methods, which fail to capture latent technical details hidden in referenced papers. Furthermore, previous approaches tend to overlook valuable implementation-level code signals and lack structured knowledge representations that support multi-granular retrieval and reuse. To overcome these challenges, we propose Executable Knowledge Graphs (xKG), a pluggable, paper-centric knowledge base that automatically integrates code snippets and technical insights extracted from scientific literature. When integrated into three agent frameworks with two different LLMs, xKG shows substantial performance gains (10.9% with o3-mini) on PaperBench, demonstrating its effectiveness as a general and extensible solution for automated AI research replication. Code is available at https://github.com/zjunlp/xKG.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17795
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations
Luo, Yujie
Yu, Zhuoyun
Wang, Xuehai
Zhu, Yuqi
Zhang, Ningyu
Wei, Lanning
Du, Lun
Zheng, Da
Chen, Huajun
Computation and Language
Artificial Intelligence
Machine Learning
Multiagent Systems
Software Engineering
Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of retrieval-augmented generation (RAG) methods, which fail to capture latent technical details hidden in referenced papers. Furthermore, previous approaches tend to overlook valuable implementation-level code signals and lack structured knowledge representations that support multi-granular retrieval and reuse. To overcome these challenges, we propose Executable Knowledge Graphs (xKG), a pluggable, paper-centric knowledge base that automatically integrates code snippets and technical insights extracted from scientific literature. When integrated into three agent frameworks with two different LLMs, xKG shows substantial performance gains (10.9% with o3-mini) on PaperBench, demonstrating its effectiveness as a general and extensible solution for automated AI research replication. Code is available at https://github.com/zjunlp/xKG.
title What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations
topic Computation and Language
Artificial Intelligence
Machine Learning
Multiagent Systems
Software Engineering
url https://arxiv.org/abs/2510.17795